Backtesting Arena

Compare 2-5 Strategies

arena_compare_strategies

Which of these strategies performed best on the same data? Run 2–5 strategies against the SAME pair, interval and date range and return per-strategy metrics plus a comparison summary (best by CAGR, best by win-rate, worst by drawdown). Use this when the user asks which of several strategies fits a market — it holds the pair, interval and requested date range fixed, which a series of separate arena_run_backtest calls does not guarantee. What it does NOT equalize is the EVALUATION window: a strategy with a long warmup starts trading later, so compare actual_date_from across the runs and check result.benchmark before ranking by CAGR. For one strategy across many pairs use arena_run_universe_backtest instead. Caveat worth passing on: comparing N strategies and reporting the winner IS multiple testing — the winner’s edge is upward-biased. arena_get_robustness_field puts a counted N on that. Sequential, expect 10–50s. Per-day quota: Pro=20, Power=200. [API Pro tier]

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "strategies": "<strategies>",
      "pair": "<pair>",
      "asset_type": "<asset_type>",
      "interval": "<interval>",
      "date_from": "<date_from>"
    },
    "name": "arena_compare_strategies"
  }
}

Input Schema

Name	Required	Description
`pair`	Yes	Crypto pair symbol, e.g. BTCUSDT — the same pair for every strategy.
`capital`	No	Starting capital in quote currency. Default 10000. Affects absolute figures only, not CAGR or win-rate.
`date_to`	No	End date, YYYY-MM-DD. Default: today.
`filters`	No	Optional entry filters (Pro+). Each one only ever REMOVES entries — filters never create trades. Omit for the unfiltered baseline.
`interval`	Yes	Candle interval: '1d' daily, '2d'/'3d' multi-day, '1w' weekly, '1M' monthly. Multi-day candles (2d/3d) are anchored to the Unix epoch, so one of n possible alignments is used. Measured on our own corpus, the choice of alignment alone moves CAGR by 6.66 pp on average (max 12.30). Treat differences below that as not distinguishable — 1d/2d/3d behaved as one block in our tests, not a ranking.
`date_from`	Yes	Start date, YYYY-MM-DD. Earlier than the pair listing is clamped to the first available candle.
`asset_type`	Yes	Asset class. Use 'crypto' unless you are explicitly backtesting a tokenized real-world asset. Note: tokenized stocks/ETFs/gold trade AS crypto pairs (e.g. spybUSDT, qqqbUSDT) — there is no separate stocks/forex backtest surface; non-crypto asset classes were retired.
`strategies`	Yes	The 2–5 strategies to compare, each with optional own params.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 29, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- removedInput schema / properties / strategies / items / additionalProperties
```
Removed value: -false
```
- addedInput schema / properties / strategies / items / properties / params / propertyNames
```
Added value: +{
+  "type": "string"
+}
```

Changed1 schema field changedSep 2, 2026

addedInput schema / properties / filters / properties / stochRsiWeekly

Added value: +{
+  "description": "Asset-specific weekly Stoch-RSI gate: entries only while the pair's weekly StochRSI(14) sits above its SMA(3). Default false.",
+  "type": "boolean"
+}

Changed4 schema fields changedAug 25, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / asset_type / description

Previous value: -"Asset class. Use 'crypto' unless you are explicitly backtesting a tokenized real-world asset."New value: +"Asset class. Use 'crypto' unless you are explicitly backtesting a tokenized real-world asset. Note: tokenized stocks/ETFs/gold trade AS crypto pairs (e.g. spybUSDT, qqqbUSDT) — there is no separate stocks/forex backtest surface; non-crypto asset classes were retired."

removedInput schema / properties / context

Removed value: -{
-  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "strategies",
-  "pair",
-  "asset_type",
-  "interval",
-  "date_from",
-  "context"
-]New value: +[
+  "strategies",
+  "pair",
+  "asset_type",
+  "interval",
+  "date_from"
+]

Changed2 schema fields changedJul 31, 2026

changedInput schema / properties / interval / description

Previous value: -"Candle interval: '1d' daily, '1w' weekly, '1M' monthly."New value: +"Candle interval: '1d' daily, '2d'/'3d' multi-day, '1w' weekly, '1M' monthly. Multi-day candles (2d/3d) are anchored to the Unix epoch, so one of n possible alignments is used. Measured on our own corpus, the choice of alignment alone moves CAGR by 6.66 pp on average (max 12.30). Treat differences below that as not distinguishable — 1d/2d/3d behaved as one block in our tests, not a ranking."

changedInput schema / properties / interval / enum

Previous value: -[
-  "1d",
-  "1w",
-  "1M"
-]New value: +[
+  "1d",
+  "2d",
+  "3d",
+  "1w",
+  "1M"
+]

Changed15 schema fields changedJul 27, 2026

addedInput schema / properties / asset_type / description

Added value: +"Asset class. Use 'crypto' unless you are explicitly backtesting a tokenized real-world asset."

addedInput schema / properties / capital / description

Added value: +"Starting capital in quote currency. Default 10000. Affects absolute figures only, not CAGR or win-rate."

addedInput schema / properties / date_from / description

Added value: +"Start date, YYYY-MM-DD. Earlier than the pair listing is clamped to the first available candle."

addedInput schema / properties / date_to / description

Added value: +"End date, YYYY-MM-DD. Default: today."

addedInput schema / properties / filters / description

Added value: +"Optional entry filters (Pro+). Each one only ever REMOVES entries — filters never create trades. Omit for the unfiltered baseline."

addedInput schema / properties / filters / properties / altcoinSeasonMode / description

Added value: +"Altcoin-Season gate. 'conservative' needs a confirmed alt season, 'aggressive' an early one. Default 'off'."

addedInput schema / properties / filters / properties / atrMode / description

Added value: +"ATR volatility regime filter. 'low'/'high' restrict entries to that volatility band, 'expansion' to rising volatility. Default 'off'."

addedInput schema / properties / filters / properties / bullmarketStageMode / description

Added value: +"Bull-market stage gate from the BTC cycle model; rising strictness from 'early' to 'strict'. Default 'off'."

changedInput schema / properties / filters / properties / minProfitGuardThreshold / description

Previous value: -"Per-trade min profit guard (negative cap, e.g. -10)."New value: +"Per-trade min profit guard (negative cap, e.g. -10 = exit once a trade is 10% under water)."

changedInput schema / properties / filters / properties / wma200 / description

Previous value: -"200-week MA filter (BTC-derived)."New value: +"200-week MA filter (BTC-derived): only take entries while BTC trades above its 200-week SMA."

addedInput schema / properties / interval / description

Added value: +"Candle interval: '1d' daily, '1w' weekly, '1M' monthly."

addedInput schema / properties / pair / description

Added value: +"Crypto pair symbol, e.g. BTCUSDT — the same pair for every strategy."

addedInput schema / properties / strategies / description

Added value: +"The 2–5 strategies to compare, each with optional own params."

addedInput schema / properties / strategies / items / properties / params / description

Added value: +"Optional per-strategy parameter overrides; omit for audited defaults."

addedInput schema / properties / strategies / items / properties / strategy / description
```
Added value: +"Strategy key — use arena_list_strategies."
```

Changed1 schema field changedJul 24, 2026

changedInput schema / properties / asset_type / enum

Previous value: -[
-  "crypto"
-]New value: +[
+  "crypto",
+  "tokenized_equity",
+  "tokenized_etf",
+  "commodities"
+]

Changed1 schema field changedJul 14, 2026

changedInput schema / properties / asset_type / enum

Previous value: -[
-  "crypto",
-  "stock",
-  "etf",
-  "commodities",
-  "forex"
-]New value: +[
+  "crypto"
+]

First observedJul 13, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only give readOnlyHint=false / idempotentHint=false / destructiveHint=false, but the description adds the crucial guarantee (pair/interval/date range held fixed) and the crucial non-guarantee (warmup can shift the evaluation window, so compare actual_date_from and check result.benchmark before ranking). It adds a statistical caveat (winner's-curse from multiple testing), points to arena_get_robustness_field, and discloses runtime (10–50s sequential), per-day quota (Pro=20, Power=200) and tier requirement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the user question and the action, then scope, then caveats, then alternatives, then operational costs — a logical order. It is long and carries several parenthetical asides, but nearly every sentence conveys a distinct constraint an agent would otherwise miss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, nested-object, multi-run comparison tool with no output schema, the description covers what is produced (per-strategy metrics plus best-by-CAGR/win-rate, worst-by-drawdown), the comparison's fairness limits, the statistical caveat with a follow-up tool, and latency/quota. Nothing material an agent needs to invoke or interpret it is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the schema already documents strategy, interval, asset_type, filters and capital in detail, so the description does not need to re-explain them. It adds a small amount of framing for results interpretation rather than parameter meaning, which lands at the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with the decision question and then states the concrete action: run 2–5 strategies against the SAME pair, interval and date range, returning per-strategy metrics plus a comparison summary naming the specific rankings (CAGR, win-rate, drawdown). This distinguishes it clearly from arena_run_backtest (single run) and arena_run_universe_backtest (one strategy, many pairs).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit trigger: 'Use this when the user asks which of several strategies fits a market.' Names both alternatives and the condition selecting each: arena_run_universe_backtest for one strategy across many pairs, and serial arena_run_backtest calls as the inferior option that does not guarantee fixed pair/interval/range.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Backtesting Arena tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.